© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 2669
    Prev
    Next
    INDEX
    Explanations

    modal verbs and expressions that convey obligation or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ssf
    -0.09
    .GetObject
    -0.07
    eyh
    -0.07
    go
    -0.06
    ivi
    -0.06
    ials
    -0.06
    zm
    -0.06
    ekt
    -0.06
    ãĥIJãĥ¼
    -0.06
    ãĥŃãĥ¼
    -0.06
    POSITIVE LOGITS
    ibrary
    0.06
    andy
    0.06
    memberof
    0.06
    iest
    0.06
    edd
    0.06
     seçenek
    0.06
    arme
    0.06
    ubi
    0.06
    747
    0.06
    istra
    0.06
    Activations Density 0.002%

    No Known Activations